mime type handling

src/paperless_tesseract/signals.py

@@ -1,5 +1,3 @@
-import re
-
 from .parsers import RasterisedDocumentParser
 
 
@@ -7,12 +5,9 @@ def tesseract_consumer_declaration(sender, **kwargs):
     return {
         "parser": RasterisedDocumentParser,
         "weight": 0,
-        "test": tesseract_consumer_test
+        "mime_types": [
+            "application/pdf",
+            "image/jpeg",
+            "image/png"
+        ]
     }
-
-
-MATCHING_FILES = re.compile(r"^.*\.(pdf|jpe?g|gif|png|tiff?|pnm|bmp)$")
-
-
-def tesseract_consumer_test(doc):
-    return MATCHING_FILES.match(doc.lower())

src/paperless_tesseract/tests/test_signals.py

@@ -1,36 +0,0 @@
-from django.test import TestCase
-
-from paperless_tesseract.signals import tesseract_consumer_test
-
-
-class SignalsTestCase(TestCase):
-
-    def test_test_handles_various_file_names_true(self):
-
-        prefixes = (
-            "doc", "My Document", "Μυ Γρεεκ Δοψθμεντ", "Doc -with - tags",
-            "A document with a . in it", "Doc with -- in it"
-        )
-        suffixes = (
-            "pdf", "jpg", "jpeg", "gif", "png", "tiff", "tif", "pnm", "bmp",
-            "PDF", "JPG", "JPEG", "GIF", "PNG", "TIFF", "TIF", "PNM", "BMP",
-            "pDf", "jPg", "jpEg", "gIf", "pNg", "tIff", "tIf", "pNm", "bMp",
-        )
-
-        for prefix in prefixes:
-            for suffix in suffixes:
-                name = "{}.{}".format(prefix, suffix)
-                self.assertTrue(tesseract_consumer_test(name))
-
-    def test_test_handles_various_file_names_false(self):
-
-        prefixes = ("doc",)
-        suffixes = ("txt", "markdown", "",)
-
-        for prefix in prefixes:
-            for suffix in suffixes:
-                name = "{}.{}".format(prefix, suffix)
-                self.assertFalse(tesseract_consumer_test(name))
-
-        self.assertFalse(tesseract_consumer_test(""))
-        self.assertFalse(tesseract_consumer_test("doc"))